© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95908
    Prev
    Next
    INDEX
    Explanations

    system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rainbow
    -0.08
     taun
    -0.08
    beiten
    -0.08
     Bernardo
    -0.08
    _bn
    -0.08
     besmet
    -0.07
     wengi
    -0.07
    .seed
    -0.07
    unen
    -0.07
     eagerly
    -0.07
    POSITIVE LOGITS
     chat
    0.07
    एफ
    0.07
     bibli
    0.07
     bibliography
    0.07
     FY
    0.07
    pragma
    0.07
     Fra
    0.07
    omics
    0.07
     Lig
    0.07
     fractions
    0.07
    Activations Density 0.002%

    No Known Activations